Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ],"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebDriver
    -0.07
     redirection
    -0.07
    (Intent
    -0.07
     March
    -0.07
     البريطاني
    -0.07
     climbing
    -0.06
     มกราคม
    -0.06
     inspiring
    -0.06
     arbitration
    -0.06
     أغسطس
    -0.06
    POSITIVE LOGITS
     "
    0.09
    _cut
    0.09
    attice
    0.08
     '
    0.08
    ilent
    0.07
    (mut
    0.07
    Eat
    0.07
     creed
    0.07
    📻
    0.07
    uke
    0.07
    Act Density 0.004%

    No Known Activations